A model calculating unit for calculating a neural layer of a multilayer perceptron model having a hardwired processor core developed in hardware for calculating a definitely specified computing algorithm in coupled functional blocks. The processor core is designed to calculate, as a function of one or multiple input variables of an input variable vector, of a weighting matrix having weighting factors and an offset value specified for each neuron, an output variable for each neuron for a neural layer of a multilayer perceptron model having a number of neurons, a sum of the values of the input variables weighted by the weighting factor, determined by the neuron and the input variable, and the offset value specified for the neuron being calculated for each neuron and the result being transformed using an activation function in order to obtain the output variable for the neuron.

A process is provided for regenerating an exhaust gas after-treatment device in an exhaust line of an internal combustion engine arrangement, the exhaust line including a particle filter. The process includes identifying when soot loading of the particle filter exceeds a predetermined level. After that, temperature of exhaust gases at the particle filter is maintained within a first temperature range until at least one of a predetermined period of time has lapsed or a determination is made that soot loading of the particle filter is below the predetermined level. After that, the temperature of the exhaust gases at the particle filter is increased to within a second temperature range above the first temperature range. An internal combustion engine arrangement is also disclosed.

A system and approach for catalyst model parameter identification with modeling accomplished by an identification procedure that may incorporate a catalyst parameter identification procedure which may include determination of parameters for a catalyst device, specification of values for parameters and component level identification. Component level identification may be of a thermal model, adsorption and desorption, and chemistry. There may then be system level identification to get a final estimate of catalyst parameters.

Methods and systems for use of model predictive control (MPC) controllers utilizing hybrid, quadratic solvers to solve a linear feasibility problem corresponding to a nonlinear problem for an internal combustion engine plant such as a diesel engine air path. The MPC solves a convex, quadratic cost function having optimization variables and constraints and directs the plant per the output solutions to optimize plant operation while adhering to regulations and constraints. The problem includes a combination of iterative and direct calculations in the primal space depending on whether a partial step (iterative) or a full step (direct) is attempted. Further, primal and dual space array matrices are pre-computed and stored offline and are retrieved via use of a unique identifier associated with a specific active set for a set of constraints. Such hybrid and/or offline calculations allow for a reduction in computational power while still maintaining accuracy of solution results.

In a case where an internal combustion engine is executing an all-cylinder operation to operate all cylinders, an air-fuel ratio estimation part of an ECU 1 estimates an air-fuel ratio of each of the cylinders by using a first observer. On the other hand, in a case where the internal combustion engine is executing a cylinder-cut operation to rest a part of the cylinders and to operate other of the cylinders, the air-fuel ratio estimation part does not estimate the air-fuel ratio of each of the cylinders by using the first observer.

Systems and methods for detecting and controlling knock in an engine are presented. In one example, engine knock sensors are selected based on whether or not certain cylinders are activated and combusting air and fuel or deactivated and not combusting air and fuel. Output of selected knock sensors is the basis for adjusting engine spark timing.

Methods and systems are provided for improving vehicle torque control accuracy. Data points of an engine torque data set are adjusted en masse by an on-board vehicle controller while also being adjusted individually by an off-board controller. By adjusting engine operation based on a torque data set that is updated by each of the on-board and off-board controllers, engine torque errors can be reliably determined and compensated for.

A system for coordinated control of an engine and associated components over various engine-modes of operation. The system may include an engine, one or more components controllable to adjust operation of the diesel engine, and a system controller. The system controller may be connected to the engine and the one or more components. The system controller may include a supervisory controller and one or more component controllers. The supervisory controller may receive system control variable set points and coordinate component control variable set points for the components to achieve the system control variable set points. The component controllers may control operation of the components to achieve the control variable set points for the components by setting manipulated variable set points for the components based on the component control variable set points and a model based non-linear dynamic inversion.

A power-based control system and method for an engine comprising a turbocharger involve obtaining a set of parameters that each affect exhaust gas energy and using the set of parameters to (i) determine a target mass flow into the engine and a target boost for the turbocharger to achieve a torque request, (ii) determine a target power for a compressor of the turbocharger to achieve the target engine mass flow and the target turbocharger boost, (iii) determine a target pressure ratio and a target mass exhaust flow for the turbine of the turbocharger to achieve a target turbine power equal to the target compressor power, and (iv) determine a target position of the wastegate valve to achieve the target turbine pressure ratio and mass exhaust flow, and commanding a wastegate valve to the target position.

Disclosed is a combustion system design method based on a target heat release rate, which belongs to the technical field of diesel engine combustion chamber design. The method includes: obtaining an ideal heat release rate based on Sabathe-Miller cycle; simulating the ideal heat release rate based on a double-Wiebe function and obtaining the target heat release rate; constructing a mapping relation among the heat release rate, piston geometric parameters and fuel injection parameters, which includes target start of combustion being an function of fuel injection timing and ignition delay, premixed combustion parameters being functions of throat radius, injection pressure and nozzle diameter, and diffusion combustion being a function of piston pit depth; solving target piston geometric parameters and target fuel injection parameters based on the mapping relation; and then designing a combustion system. The method does not depend on experience and multi-scheme design, greatly shortens the combustion system design.